Medicine
HAIID
HAIID measures whether people revise their answers on classification tasks, such as spotting sarcasm or judging skin lesion photographs, after seeing advice presented as coming either from an AI algorithm or from a human peer. The advice itself is identical in both cases.
152items
1,127subjects
MITlicense
medicinedomain
nlp_taskdomain
reasoningdomain
culturaldomain
textmodality
imagemodality
item-level responses released
Saturation status: Yes
Response matrix
Loading session strips…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect